Article Per Year (5 Year)
p-Index From 2021 - 2026
2.392
P-Index
This Author published in this journals
All Journal Techno.Com: Jurnal Teknologi Informasi Register: Jurnal Ilmiah Teknologi Sistem Informasi Indonesian Journal of Artificial Intelligence and Data Mining ILKOM Jurnal Ilmiah Jurnal Nasional Komputasi dan Teknologi Informasi Jurnal Sains dan Informatika : Research of Science and Informatic Ensiklopedia of Journal Journal of Applied Data Sciences JPM: JURNAL PENGABDIAN MASYARAKAT IndraTech JUSTIN (Jurnal Sistem dan Teknologi Informasi) Jurnal Pengabdian Masyarakat Nasional Jurnal ilmiah teknologi informasi Asia
Karfindo, Karfindo
Unknown Affiliation
Religion Aerospace Engineering Arts Humanities Astronomy Automotive Engineering Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Environmental Science Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Materials Science & Nanotechnology Medicine & Pharmacology Neuroscience Public Health Social Sciences Transportation Other

Published : 17 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 17 Documents
Search

 1   2 
Optimalisasi Klasifikasi Umpan Balik Mahasiswa Terhadap Layanan Kampus dengan Sinergi Random Forest dan Smote Karfindo Karfindo; Rifa Turaina; Rusli Saputra
Jurnal Nasional Komputasi dan Teknologi Informasi (JNKTI) Vol 6, No 6 (2023): Desember 2023
Publisher : Program Studi Teknik Komputer, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/jnkti.v6i6.7269

Abstract

Abstrak - Di era digital, pendidikan tinggi dihadapkan pada tantangan untuk merespons secara efektif terhadap umpan balik mahasiswa, yang merupakan kunci untuk meningkatkan kualitas layanan kampus. Penelitian ini dirancang untuk mengoptimalkan proses klasifikasi umpan balik tersebut dengan menggunakan sinergi antara algoritma Random Forest dan teknik Synthetic Minority Over-sampling Technique (SMOTE) dalam analisis sentimen. Data dikumpulkan dari berbagai saran mahasiswa, diikuti dengan tahapan pra-pemrosesan yang meliputi pembersihan, tokenisasi, dan penghapusan stopwords. Setelah pelabelan sentimen menggunakan lexicon yang terverifikasi, SMOTE diterapkan untuk mengatasi ketidakseimbangan kelas dalam dataset. Hasil menunjukkan bahwa sebelum penerapan SMOTE, terdapat bias terhadap kelas mayoritas, namun setelah aplikasi SMOTE, terjadi peningkatan yang signifikan dalam presisi dan recall terutama pada kelas minoritas, meningkatkan akurasi klasifikasi secara keseluruhan. Hasil ini menggarisbawahi pentingnya penerapan teknik penyeimbangan data dalam analisis sentimen, menunjukkan bahwa pendekatan ini dapat memberikan wawasan yang lebih seimbang dan mendalam, serta mendukung institusi dalam membuat keputusan yang tepat dan responsif terhadap kebutuhan mahasiswa..Kata kunci: Analisis Sentimen, Klasifikasi Teks, Random Forest, SMOTE. Abstract - In the digital age, higher education faces the challenge of effectively responding to student feedback, which is key to enhancing campus service quality. This study is designed to optimize the feedback classification process by leveraging the synergy between the Random Forest algorithm and the Synthetic Minority Over-sampling Technique (SMOTE) in sentiment analysis. Data was collected from various student suggestions, followed by preprocessing stages that included cleaning, tokenization, and the removal of stopwords. After sentiment labeling using a verified lexicon, SMOTE was applied to address class imbalances in the dataset. The results indicate that before the application of SMOTE, there was a bias toward the majority class, but after the application of SMOTE, there was a significant improvement in precision and recall, especially for the minority classes, enhancing the overall classification accuracy. These findings underscore the importance of applying data balancing techniques in sentiment analysis, demonstrating that this approach can provide more balanced and in-depth insights, as well as support institutions in making accurate and responsive decisions to student needs.Keywords: Sentiment Analysis, Text Classification, Random Forest, SMOTE.
SISTEM PENDUKUNG KEPUTUSAN PENERIMA BEASISWA MENGGUNAKAN METODE WEIGHTED PRODUCT Turaina, Rifa; Karfindo, Karfindo
Ensiklopedia of Journal Vol 4, No 1 (2021): Vol 4 No. 1 Edisi 2 Oktober 2021
Publisher : Lembaga Penelitian dan Penerbitan Hasil Penelitian Ensiklopedia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1161.414 KB) | DOI: 10.33559/eoj.v3i5.987

Abstract

Scholarship is one of the school programs to help ease the burden on parents of students to ease the burden of education costs for students. SMP N 2 Sungayang, there is also a scholarship program aimed at students, both deserving and underprivileged and of course based on predetermined criteria. To help schools determine students who are eligible to receive scholarships, a Decision Support System (SPK) can be used, where one of the decision methods that can be used is the Weighted Product (WP) method. Weighted Product is a method used to find several students from a number of students with certain criteria. The result of this research is an SPK application that can assist the school in determining who is entitled to receive a scholarship based on predetermined criteria and weights.
Comparison Analysis of HSV Method, CNN Algorithm, and SVM Algorithm in Detecting the Ripeness of Mangosteen Fruit Images Anam, M. Khairul; Sumijan, Sumijan; Karfindo, Karfindo; Firdaus, Muhammad Bambang
Indonesian Journal of Artificial Intelligence and Data Mining Vol 7, No 2 (2024): September 2024
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v7i2.29739

Abstract

Mangosteen contains a substance known as Xanthone, a phytochemical compound with the distinctive red component in mangosteen that is known for its properties as an anticancer, antibacterial, and anti-inflammatory agent. Additionally, Xanthone has the potential to strengthen the immune system, promote overall health, support mental well-being, maintain microbial balance in the body, and improve joint flexibility. The mangosteen fruit is consumable when it reaches maturity, displaying a dark purplish-black color. Besides the edible part of the fruit, the peel also possesses remarkable medicinal properties. To detect whether the fruit is ripe or not, this research employs image processing techniques. The study utilizes the HSV (Hue, Saturation, and value) color space method, CNN (Convolutional Neural Network) algorithm, and SVM (Support Vector Machine) algorithm. These methods and algorithms are chosen for their relatively high accuracy levels. The dataset used in this research is obtained from mangosteen datasets available on Kaggle. The results of this study indicate that the HSV method achieved an accuracy of 86.6%, SVM achieved an accuracy of 87%, and CNN achieved an accuracy of 91.25%. From the achieved accuracies, it is evident that the CNN algorithm yields higher accuracy compared to the others.
Deteksi Dini Masalah dalam Proses Belajar Mengajar Secara Daring Menggunakan Sistem AT-OLP Karfindo Karfindo; Rifa Turaina
Jurnal Ilmiah Teknologi Informasi Asia Vol 15 No 2 (2021): Volume 15 Nomor 2 (8)
Publisher : LP2M INSTITUT TEKNOLOGI DAN BISNIS ASIA MALANG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32815/jitika.v15i2.485

Abstract

Masa pandemi covid-19 memaksa banyaknya sektor di berbagai bidang untuk melakukan pekerjaan dari rumah, begitu juga dalam bidang pendidikan. Berbagai sekolah mulai dari tingkat dasar sampai tingkat perguruan tinggi, diminta untuk melaksanakan proses belajar mengajar dari rumah secara online atau yang biasa disebut dengan pembelajaran daring. Pemanfaatan e-learning memang membantu dalam pelaksanaan pembelajaran daring, sehingga membuat mahasiswa belajar mandiri dan motivasi meningkat namun ada kesulitan yang terjadi dalam mengontrol pelaksanaan pembelajaran daring sehingga mahasiswa tidak terawasi dengan efektif. Metode penelitian yang digunakan dalam penelitian ini adalah metode FAST karena kerangka kerjanya yang cukup fleksibel untuk berbagai jenis proyek dan strategi. Untuk melakukan control maka digunakan sistem AT-OTP adalah sistem yang digunakan untuk melakukan monitoring terhadap kegiatan proses belajar mengajar secara daring, dengan menggunakan konsep keterbukaan terhadap semua aktifitas yang dilakukan. Sehingga dengan adanya saling terbuka maka masalah yang dihadapi bisa segara diketahui dan dicarikan solusi terhadap permasalah tersebut. Kata Kunci : Pembelajaran daring, e-learning, system AT-OTP
Enhancing the Performance of Machine Learning Algorithm for Intent Sentiment Analysis on Village Fund Topic Anam, M. Khairul; Putra, Pandu Pratama; Malik, Rio Andika; Karfindo, Karfindo; Putra, Teri Ade; Elva, Yesri; Mahessya, Raja Ayu; Firdaus, Muhammad Bambang; Ikhsan, Ikhsan; Gunawan, Chichi Rizka
Journal of Applied Data Sciences Vol 6, No 2: MAY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i2.637

Abstract

This study explores the implementation of Intent Sentiment Analysis on Twitter data related to the Village Fund program, leveraging Multinomial Naïve Bayes (MNB) and enhancing it with Synthetic Minority Over-sampling Technique (SMOTE) and XGBoost (XGB). The analysis categorizes tweets into six labels: Optimistic, Pessimistic, Advice, Satire, Appreciation, and No Intent. Initially, the MNB model achieved an accuracy of 67% on a 90:10 data split. By applying SMOTE, accuracy improved by 12%, reaching 89%. However, adding Chi-Square feature selection did not increase accuracy further. Incorporating XGB into the MNB+SMOTE model led to a 6% improvement, achieving a final accuracy of 95%. Comprehensive model evaluation revealed that the MNB+SMOTE+XGB model achieved 96% accuracy, 96% precision, 96% recall, and a 96% F1-score, with an AUC of 99%, categorizing it as excellent. These findings demonstrate that the combination of SMOTE for addressing class imbalance and XGBoost for boosting performance significantly enhances the MNB model's classification capabilities. The novelty lies in the integration of these techniques to improve intent sentiment classification for public opinion analysis on the Village Fund program. The results indicate that the majority of tweets labeled as "No Intent" reflect a lack of specific sentiment or actionable intent, providing valuable insights into public perception of the program.
Transformasi Pembelajaran Digital Inklusif Berbasis RS-BPBL© EduLink pada Anak Yatim Piatu Duafa Binaan Masjid: Model Masjid EduTech Wahyudi, Wahyudi; Karfindo, Karfindo; Meta, Monanda Rio; Zakki, Aulia Ahmad; Ajwari, Ridwan
JPM: Jurnal Pengabdian Masyarakat Vol. 6 No. 2 (2025): October 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/jpm.v6i2.2666

Abstract

The digital divide among underprivileged orphaned children (AYPD) remains a key barrier to inclusive education. This community service program aimed to improve digital literacy, independent learning, and social participation of AYPD through the implementation of RS-BPBL© EduLink, positioning the mosque as a community learning hub. The program was conducted at Masjid As-Salaam, Padang, in five stages: socialization, training, technology implementation, mentoring, and sustainability. Evaluation was carried out through pre–post tests, activity logs, and showcase products. The results demonstrated significant improvements in knowledge (84.5%) and digital skills (85.7%), full adoption of the LMS (100% of participants), and 85% successfully managing independent study schedules for 6 weeks. Three showcases were conducted as authentic assessments that fostered reflection and social accountability. The program confirmed the effectiveness of the Masjid EduTech model in bridging the digital divide while strengthening community-based learning ecosystems. This initiative holds strong replication potential in other communities and aligns with SDG 4 (Quality Education), Asta Cita (human capital development), and Indonesia’s higher education strategic agenda.
PEMANFATAAN APLIKASI E-SAWIT KITA SEBAGAI MEDIA PEMBELAJARAN SERTA MENCIPTAKAN INFORMASI AKTUAL DAN KOLABORASI ANTAR PETANI SAWIT Andesti, Cyntia Lasmi; Amuharnis, Amuharnis; Sirait, Weri; Nurhidayat, Nurhidayat; Lonanda, Fitria; Karfindo, Karfindo; Dian, Rahmad
Jurnal Pengabdian Masyarakat Nasional Vol 4, No 2 (2024)
Publisher : Universitas Mercu Buana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22441/pemanas.v4i2.30168

Abstract

The use of information technology in the agricultural sector is increasingly important to increase productivity and collaboration between farmers. This training explores the use of the E-Sawit Kita application as a learning medium and means of creating actual information for palm oil farmers. This training provides educational material related to best cultivation practices, land management and relevant market information. In addition, this research also involves intensive training for farmers in using the application, with the aim of increasing their understanding and skills in utilizing this technology. With interactive features, E-Sawit Kita allows farmers to share experiences, challenges and solutions, which in turn strengthens the collaborative network between them. The method used in this training is in the form of lectures, training material and questions and answers about using the E-Sawit Kita application. The research results show that E-Sawit Kita, through the training it provides, not only increases farmers' knowledge and skills, but also strengthens community solidarity through continuous exchange of information. These findings provide valuable insights for the development of similar applications to support sustainable agriculture in Indonesia.
Co-Authors Ajwari, Ridwan Amuharnis Anam, M Khairul arman, arman Cyntia Lasmi Andesti Elva, Yesri Firdaus, Muhammad Bambang Gunawan, Chichi Rizka Heru Saputra Ikhsan Ikhsan Ilfa Stephane Indradewa, Rhian Jelita, Silis Lonanda, Fitria Mahessya, Raja Ayu Meta, Monanda Rio Mustafa, Firlan Mustafa, Firlan Nurhidayat Nurhidayat Pandu Pratama Putra, Pandu Pratama Putra, Lakry Maltaf Rahmad Dian Rifa Turaina Rio Andika Malik Rusli Saputra Silis Jelita Sumijan Sumijan Teri Ade Putra Wahyudi Wahyudi Weri Sirait Zakki, Aulia Ahmad